CN107302496B - Software defined network link failure recovery method based on in-band control - Google Patents
Software defined network link failure recovery method based on in-band control Download PDFInfo
- Publication number
- CN107302496B CN107302496B CN201710384178.4A CN201710384178A CN107302496B CN 107302496 B CN107302496 B CN 107302496B CN 201710384178 A CN201710384178 A CN 201710384178A CN 107302496 B CN107302496 B CN 107302496B
- Authority
- CN
- China
- Prior art keywords
- link
- path
- network
- switch
- controller
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/124—Shortest path evaluation using a combination of metrics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/22—Alternate routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/28—Routing or path finding of packets in data switching networks using route fault recovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/55—Prevention, detection or correction of errors
- H04L49/557—Error correction, e.g. fault recovery or fault tolerance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
Abstract
The invention discloses a software defined network link fault recovery method based on in-band control, and belongs to the technical field of communication networks. Firstly, an SDN controller acquires the whole network topology by using an LLDP protocol, generates a control network, calculates a backup path for a link on the control network and sends the backup path to a corresponding group table. And then, once the link fails, the switch sends the failure information to the controller, triggers the switch to feed back the real-time traffic information of the network to the controller, and the controller updates the network topology and the traffic information. And finally, calculating the sum of the resource consumption of the path and the cost of the link according to the current network topology and the current flow information, so as to select the optimal recovery path and send the flow table to the corresponding switch, thereby realizing the recovery of the link failure. In the in-band control network, the system adopts a backup path for restoring the control flow and adopts self-adaptive restoration to the data flow, thereby realizing reasonable distribution of link resources during fault restoration and improving the overall performance of the network.
Description
Technical Field
The invention belongs to the technical field of communication networks, and relates to a software defined network link fault recovery method based on in-band control.
Background
Due to the restriction of economic factors, low-cost network equipment is generally adopted in a large-scale network, so that various faults such as link failure, server failure and switch failure exist, the probability of occurrence of link failure within one year is about 30% according to statistics, and the phenomenon is common in the network. Therefore, failure recovery strategies and fault tolerance mechanisms for guaranteeing reliable service capability of the network have become problems to be solved urgently in current research. Fault management for SDNs differs from traditional networks in many ways. In conventional networks, upon a link failure, a distributed network device (e.g., a router) reconstructs a routing path and updates a routing table based on the changed topology information. However, in SDN networks, routing decisions are made by a centralized controller. The controller detects the topology change, performs path calculation according to the whole network information, and installs a flow table of the switch along the routing path. The link failure recovery mechanism in the SDN mainly includes a protection mechanism and a recovery mechanism.
Documents [ Adrichem N LM V, Asten B J V, Kuipers F a. fast Recovery in Software-Defined Networks [ C ]// Third European works on Software Defined Networks. bucket: IEEE Press,2014:61-66 ] use a fast failover mechanism provided by a group table of OpenFlow to implement a failure Recovery of an SDN network, which also calculates a Recovery path to an end node for each switch through which each flow passes when calculating a working path. If no path is available after the fault occurs, the data packet is forwarded to the upper-level node by a backtracking routing method. After the link failure is recovered, the group table redistributes the data flow to the original working path; the document [ AdamiD, Giordano S, Pagano M, et al, class-based traffic recovery with load balancing in software-defined networks [ C ]// GLOBECOMWorks. Austin: IEEE Press,2014: 161-.
Through research on fault recovery in the existing SDN, the current solutions for the problem of link fault in the SDN mostly focus on adopting a local recovery mode to backup a path, but the recovery mode does not fully utilize the characteristic of centralized control of an SDN framework and does not consider the distribution condition of the flow of the whole network after fault recovery.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. A software defined network link failure recovery method based on in-band control is provided, which balances traffic on links with higher bandwidth utilization. The technical scheme of the invention is as follows:
a software defined network link failure recovery method based on in-band control comprises the following steps:
101. the SDN controller initializes a network topology and generates a backup path of a control network and a link thereof;
102. when the data layer link fails and the failed link belongs to the control network, the switch switches the forwarding path by using the fast failure switching group table, and recovers the transmission of the control flow, otherwise, the switch directly goes to the step 103;
103. the switch sends the fault information to the controller, triggers the switch to feed back real-time state information of the network to the controller, and calculates the first K shortest paths between source and destination nodes according to the current network topology and the time delay weight;
104. according to the real-time flow information, calculating the sum of the link cost values of the first K shortest paths in the step 103 and the resource consumption rate of the paths;
105. and setting a target function according to the sum of the calculated link cost and the resource consumption rate of the path, and finally selecting the optimal recovery path and issuing a flow table item.
Further, in step 101, the SDN controller grasps global topology information by using an LLDP protocol, calculates a shortest path tree using the SDN controller as a root node by using a Dijkstra algorithm, and issues a flow entry to a corresponding switch, and at the same time, calculates a backup path for a link on the control network, and issues a group entry to the corresponding switch.
Further, the link failure detection of step 102 is to add BFD protocol to the switch, so that
The link status is detected by periodically sending detection messages between the nodes.
Further, the step 103 of calculating the first K shortest paths between the source and destination nodes according to the current network topology and the delay weight specifically includes: firstly, the shortest path from an upstream node s of a fault link to a destination node t is calculated, and a time delay weight of the path is calculated; then, after links on the shortest path are removed in sequence, the secondary short path and the time delay weight are obtained; and finally, sequencing the time delay weights of the paths to obtain the first K shortest paths as alternative paths.
Further, the step 104 defines a link cost function and a path consumption rate, and the link cost function is measured by the link utilization rate, that is
Wherein the link utilization
Link loadi,j(t) monitoring the flow information of each port and each link of the switch in real time by a controller to obtain phie(t) indicates that the higher the link utilization in the network, the higher the link cost;
the resource consumption rate of the path (s, t) is
Namely:
wherein Z isp(s, t) represents the efficiency of the path (s, t) as the average of the sum of the reciprocal distances from the node s to other nodes on the path (s, t), | p | represents the number of nodes on the path, ds,kThe distance from node s to node k is represented by the number of hops.
Further, said step 105 defines the objective function as P, which is expressed as follows:
when calculating the restoration path, the weight of the cost and the resource consumption rate of the restoration path can be determined by adjusting the coefficient α, and the value interval of α is [0,1 ].
The invention has the following advantages and beneficial effects:
the invention provides a link failure recovery method, firstly, initializing a network topology, and generating a backup path of a control network and a link thereof; then, once the link fails, the switch sends the failure information to the controller, triggers the switch to feed back real-time flow information of the network to the controller, and the controller updates the network topology and the flow information; and finally, calculating the sum of the cost of the link and the resource consumption of the path according to the current network topology and the current flow information so as to select the optimal recovery path, and issuing the related flow table items to the corresponding switch by the controller to realize the recovery of the link failure.
In the in-band control network, the invention adopts the backup path to recover aiming at the control flow and adopts the self-adaptive recovery to the data flow, thereby realizing the reasonable distribution of link resources when the fault is recovered and improving the overall performance of the network. The specific innovation is embodied in the computation of the restoration path of the data stream in steps 103, 104 and 105.
Drawings
FIG. 1 is a schematic flow diagram of a preferred embodiment of the present invention;
FIG. 2 is a diagram of a custom network topology provided in accordance with an embodiment of the present invention;
FIG. 3 is an overall architecture of the present invention;
FIG. 4 is a graph of the average bandwidth utilization for three combinations;
fig. 5 is a diagram comparing the three algorithms for the link load change in the customized network topology.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
in this embodiment, a Mininet simulation platform is selected to perform a functional test of the system, and each functional module designed by the present invention is implemented by using a Ryu controller based on Python programming language, so that the function of OpenvSwitch is extended for detecting a link failure.
The technical scheme of the invention is shown in figure 1:
firstly, the controller grasps the global topology information by utilizing an LLDP protocol, calculates a shortest path tree with the controller as a root node by adopting a Dijkstra algorithm, and transmits a flow table item to a corresponding switch. And meanwhile, a backup path is calculated for a link on a control network, and a group table entry is issued to a corresponding switch.
And secondly, adding a BFD protocol into the switch, and detecting the link state by periodically sending detection messages among the nodes. When a link failure occurs, if a failed link belongs to a control network, transmission of a control flow is affected, and a switch needs to switch a forwarding path by using a fast failover group table to recover transmission of the control flow.
Thirdly, firstly, calculating the shortest path from the upstream node s of the fault link to the destination node t, and solving the time delay weight of the path; then, after links on the shortest path are removed in sequence, the secondary short path and the time delay weight are obtained; and finally, sequencing the time delay weights of the paths to obtain the first K shortest paths as alternative paths. In this embodiment, K is taken to be 3, and fig. 2 is a simulation topological graph of the present invention
Fourth, a link cost function and a path consumption rate are defined, the link cost function being measured by link utilization, i.e.
Wherein the link utilization
Link loadi,jAnd (t) monitoring the flow information of each port and each link of the switch in real time through the controller to obtain the flow information. Phi is aeAnd (t) represents that the higher the link utilization rate in the network is, the higher the link cost is, and the punitive high cost is given to the overloaded link so as to realize the load balance of the network and avoid the occurrence of network congestion.
The resource consumption rate of the path (s, t) is
Namely:
wherein Z isp(s, t) represents the efficiency of the path (s, t) and is the average of the sum of the reciprocal distances from the node s to other nodes on the path (s, t). | p | represents the number of nodes on the path, ds,kThe distance from node s to node k is represented by the number of hops.
And fifthly, comprehensively considering the load condition of the current link of the recovery path and the network resources which can be consumed so as to guarantee the overall performance of the network during fault recovery, carrying out weighted summation on the link cost of the available path and the resource consumption rate, and then evaluating the path, wherein an objective function is defined as P and expressed as follows:
when calculating the restoration path, the weight of the cost and the resource consumption rate of the restoration path may be determined by adjusting the coefficient α, and the value interval of α is [0,1 ]. in this embodiment, α is equal to 0.5.
Fig. 3 shows an overall architecture of the fault recovery system according to the present invention, which mainly includes a topology discovery module for acquiring the entire network topology during initialization; the link information set module is used for acquiring real-time state information of the port of the switch and providing data support for calculating a recovery path; the link fault detection module is used for detecting link faults in time and sending fault messages to the controller; and the path calculation module is used for calculating a recovery path for the fault link according to the acquired real-time network state after the controller receives the link fault message.
FIG. 4 tests control and data flows in combination with both Protection and recovery failure recovery mechanisms. The following three combinations were mainly tested: the Restoration mechanism (C-rest, D-rest) is adopted for both the control flow and the data flow; the control flow adopts a Protection mechanism and the data flow adopts a Restoration mechanism (C-prot, D-rest); both control and data flows use the Protection mechanism (C-prot, D-prot). In the experiment, the traffic sending rate of h1 is sequentially increased, 9 groups of data are tested from 0.5Mbps to 4.5Mbps, and the average bandwidth utilization rate of the network is calculated, and the experimental result is shown in fig. 4. When the traffic sending rate is 0.5Mbps to 2Mbps, although the average bandwidth utilization rate of the (C-prot, D-rest) combination is smaller than that of the (C-prot, D-prot) combination, the difference is smaller. As the traffic sending rate increases, the average bandwidth utilization of the (C-prot, D-rest) combination is better than that of the (C-prot, D-prot) combination, and the difference gradually increases. The reason is that as the sending rate increases, the network may be congested, and in addition, link failure occurs, the (C-prot, D-prot) combination may cause the packet loss number to increase sharply, thereby affecting the average link utilization of the network, and the (C-prot, D-rest) combination may select a restoration path according to the link load condition, thereby reducing the occurrence of network congestion. The average link utilization of the (C-rest, D-rest) combination is always lower than that of the (C-prot, D-rest) combination due to the longer recovery time required.
Fig. 5 is a graph for verifying the performance of the CA-FC algorithm proposed by the present invention by comparing with a currently commonly used failure recovery scheme (FRA) and a failure recovery scheme (CNV) considering a load. In fig. 5, BL is the bandwidth utilization of each link before the failure occurs. As can be seen from fig. 5(a), after the link < S1, S3> (link No. 2) on the primary path fails, the algorithm CA-FC provided by the present invention selects the backup path (S1-S2-S5-S8) which is the same as the FRA, and the CNV performs classified transmission by streaming, thereby well balancing the traffic on the link with higher bandwidth utilization. Fig. 5(b) injects a large number of additional data streams on the backup links < S2, S5> simulating a high load situation. As can be seen from fig. 5(b), after the link No. 2 fails, the utilization rate of the link No. 4 on the FRA-configured backup path (S1-S2-S5-S8) reaches 0.9, while the bandwidth utilization rate of other links is less than 0.1. CNV except for the increase in bandwidth utilization of link No. 4, other links do not change much from fig. 5 (a). The algorithm CA-FC provided by the invention selects backup paths according to the real-time network condition under the condition of high load of the No. 4 link (S1-S4-S7-S8).
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (4)
1. A software defined network link failure recovery method based on in-band control is characterized by comprising the following steps:
101. the SDN controller initializes a network topology and generates a backup path of a control network and a link thereof;
102. when the data layer link fails and the failed link belongs to the control network, the switch switches the forwarding path by using the fast failure switching group table, and recovers the transmission of the control flow, otherwise, the switch directly goes to the step 103;
103. the switch sends the fault information to the controller, triggers the switch to feed back real-time state information of the network to the controller, and calculates the first K shortest paths between source and destination nodes according to the current network topology and the time delay weight; the step 103 of calculating the first K shortest paths between the source and destination nodes according to the current network topology and the delay weight specifically includes: firstly, the shortest path from an upstream node s of a fault link to a destination node t is calculated, and a time delay weight of the path is calculated; then, after links on the shortest path are removed in sequence, the secondary short path and the time delay weight are obtained; finally, sorting the time delay weight values of the paths to obtain the first K shortest paths as alternative paths;
104. according to the real-time flow information, calculating the sum of the link cost values of the first K shortest paths in the step 103 and the resource consumption rate of the paths; the step 104 defines a link cost function and a path consumption rate, the link cost function being measured by link utilization, i.e. the link cost function is measured by link utilization
Wherein the link utilization
Link loadi,j(t) monitoring the flow information of each port and each link of the switch in real time by a controller to obtain phie(t) indicates that the higher the link utilization in the network, the higher the link cost;
the resource consumption rate of the path (s, t) is
Namely:
wherein Z isp(s, t) represents the efficiency of the path (s, t) as the average of the sum of the reciprocal distances from the node s to other nodes on the path (s, t), | p | represents the number of nodes on the path, ds,kRepresenting the distance from the node s to the node k by the hop count;
105. and setting a target function according to the sum of the calculated link cost and the resource consumption rate of the path, and finally selecting the optimal recovery path and issuing a flow table item.
2. The in-band control-based software-defined network link failure recovery method of claim 1, wherein in the step 101, the SDN controller grasps global topology information by using an LLDP protocol, calculates a shortest path tree using the SDN controller as a root node by using a Dijkstra algorithm, and issues flow entries to corresponding switches, and calculates backup paths for links on the control network, and issues group entries to corresponding switches.
3. The in-band control-based software defined network link failure recovery method according to claim 1, wherein the link failure detection in step 102 is to add BFD protocol in the switch and detect the link status by periodically sending detection messages between nodes.
4. The in-band control-based software defined network link failure recovery method of claim 1, wherein said step 105 defines an objective function as P, expressed as follows:
when calculating the restoration path, the weight of the cost and the resource consumption rate of the restoration path can be determined by adjusting the coefficient α, and the value interval of α is [0,1 ].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384178.4A CN107302496B (en) | 2017-05-26 | 2017-05-26 | Software defined network link failure recovery method based on in-band control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384178.4A CN107302496B (en) | 2017-05-26 | 2017-05-26 | Software defined network link failure recovery method based on in-band control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107302496A CN107302496A (en) | 2017-10-27 |
| CN107302496B true CN107302496B (en) | 2020-03-17 |
Family
ID=60137257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710384178.4A Active CN107302496B (en) | 2017-05-26 | 2017-05-26 | Software defined network link failure recovery method based on in-band control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107302496B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107483109B (en) * | 2017-08-09 | 2020-04-24 | 天津大学 | Method for rapidly positioning fault in data center network |
| CN108092895B (en) * | 2017-12-26 | 2020-07-14 | 重庆邮电大学 | Software Defined Network (SDN) joint routing selection and network function deployment method |
| CN108075825B (en) * | 2018-01-24 | 2020-06-30 | 大连大学 | SDN-based multi-controller failure processing method for space-based information network |
| CN109980647B (en) * | 2018-12-20 | 2020-08-04 | 广东电网有限责任公司 | Power distribution network fault load transfer power supply and recovery method |
| CN109768924B (en) * | 2019-02-14 | 2021-06-08 | 山东省计算中心（国家超级计算济南中心） | SDN network multilink fault recovery method and system oriented to multi-stream coexistence |
| CN110034955B (en) * | 2019-03-26 | 2022-03-22 | 重庆邮电大学 | Target controller selection method considering multiple switch migration indexes |
| CN109981493B (en) * | 2019-04-09 | 2020-05-01 | 苏州浪潮智能科技有限公司 | Method and device for configuring virtual machine network |
| CN110113258B (en) * | 2019-04-23 | 2024-03-26 | 北京全路通信信号研究设计院集团有限公司 | Method and system for automatically protecting data surface link by using control surface link |
| CN110753054A (en) * | 2019-10-25 | 2020-02-04 | 电子科技大学 | Anonymous communication method based on SDN |
| CN112564964B (en) * | 2020-12-04 | 2022-06-24 | 中国石油大学(华东) | Fault link detection and recovery method based on software defined network |
| CN113709030B (en) * | 2021-08-27 | 2024-04-23 | 新华三大数据技术有限公司 | Control method and device for network traffic and electronic equipment |
| CN113839886B (en) * | 2021-09-18 | 2023-04-18 | 北京邮电大学 | Fault processing method and device for photoelectric hybrid switching network, electronic equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103763207A (en) * | 2014-01-29 | 2014-04-30 | 杭州华三通信技术有限公司 | In-band control connection establishment method and device in SDN |
| CN103986651A (en) * | 2014-05-30 | 2014-08-13 | 杭州华三通信技术有限公司 | SDN controller and control method thereof |
| EP2782291A1 (en) * | 2013-03-20 | 2014-09-24 | Wolting Holding B.V. | Compiler for and method of software defined networking |
-
2017
- 2017-05-26 CN CN201710384178.4A patent/CN107302496B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2782291A1 (en) * | 2013-03-20 | 2014-09-24 | Wolting Holding B.V. | Compiler for and method of software defined networking |
| CN103763207A (en) * | 2014-01-29 | 2014-04-30 | 杭州华三通信技术有限公司 | In-band control connection establishment method and device in SDN |
| CN103986651A (en) * | 2014-05-30 | 2014-08-13 | 杭州华三通信技术有限公司 | SDN controller and control method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107302496A (en) | 2017-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107302496B (en) | Software defined network link failure recovery method based on in-band control | |
| CN105379196B (en) | Method, system and computer storage medium for the routing of fault-tolerant and load balance | |
| JP6062939B2 (en) | Self-healing recognizable hybrid design of controller-switch connectivity in split architecture system | |
| CN109768924B (en) | SDN network multilink fault recovery method and system oriented to multi-stream coexistence | |
| Lee et al. | Path layout planning and software based fast failure detection in survivable OpenFlow networks | |
| Kanagevlu et al. | SDN controlled local re-routing to reduce congestion in cloud data center | |
| CN106411766A (en) | Flow scheduling system and method based on SDN | |
| US7543057B1 (en) | Method for monitoring a network | |
| EP2656548A1 (en) | Communications network management | |
| CN105634823B (en) | A kind of data center network fault recovery method based on multirouting configuration | |
| CN107888490B (en) | Message forwarding method, routing delay calculation and scheduling device and system | |
| CN112350949B (en) | Rerouting congestion control method and system based on flow scheduling in software defined network | |
| CN105406988A (en) | Software-definition survivable network construction method | |
| CN103139069A (en) | Multi-measurement-parameter communication network route method based on analytic hierarchy process (AHP) | |
| CN111565146A (en) | Network topology aware power communication network link fault recovery algorithm | |
| Wang et al. | An ACO-based elephant and mice flow scheduling system in SDN | |
| Vanamoorthy et al. | Congestion-free transient plane (CFTP) using bandwidth sharing during link failures in SDN | |
| Fatmi et al. | Distributed multipath routing for data center networks based on stochastic traffic modeling | |
| Braun et al. | Load-dependent flow splitting for traffic engineering in resilient OpenFlow networks | |
| CN109873762B (en) | Path scheduling method, path scheduling device and computer-readable storage medium | |
| US20230017561A1 (en) | Network Device, System and Method For Cycle-Based Load Balancing | |
| Huynh et al. | Cross-over spanning trees enhancing metro ethernet resilience and load balancing | |
| Ya et al. | Multipath fault-tolerance routing mechanism in data center network | |
| Liu et al. | Disturbance based dynamic load balancing routing mechanism under SDN | |
| Cheng et al. | Cross-layer geodiverse protocol stack for resilient multipath transport and routing using OpenFlow |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |